K12-Bench - Chemistry: leaderboard
Metric: Chemistry subset, exact match (%, all-or-nothing over the selected option set) on four-option multi-select questions generated from the K12-KGraph curriculum knowledge graph of Chinese K-12 mathematics, physics, chemistry and biology textbooks; zero-shot, answer-only, temperature 0, all five tasks; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 53.6 |
| 2 | Gemini 2.5 Flash | 45 |
| 3 | Gemma 4 31B (IT) | 44.1 |
| 4 | GPT-5.2 | 39.9 |
| 5 | Qwen 3 32B | 39.8 |
| 6 | GPT-5 Mini | 29.8 |
| 7 | GPT-4o | 29.2 |
| 8 | GLM-4.7 Flash | 28.8 |
| 9 | Llama 3 8B Instruct | 8.1 |
Interactive version: theaggregate.ai/benchmark?slug=k12-bench-chemistry · How It Works · Data refreshed daily, snapshot 2026-10-07.